{"id":"W2049975772","doi":"10.1109/icip.2013.6738708","title":"Combination of thermal and color images for accurate foreground / background segmentation in outdoor environment","year":2013,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Institut National d'Optique","funders":"","keywords":"Ground truth; Artificial intelligence; Computer science; Computer vision; Segmentation; Visibility; Pixel; Context (archaeology); Image segmentation; Color space; Pattern recognition (psychology); Image (mathematics); Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004214463,0.00007120663,0.0001128711,0.00005434228,0.0000328971,0.00008309158,0.0001322511,0.00002969518,0.00001879888],"category_scores_gemma":[0.00001286059,0.00005888714,0.00002101543,0.00006412034,0.00003382348,0.0007258626,0.00005268218,0.00002820161,0.000005932917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002447624,"about_ca_system_score_gemma":0.000009232985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000866389,"about_ca_topic_score_gemma":0.00001039816,"domain_scores_codex":[0.9993559,0.00006585438,0.000186131,0.0001750886,0.00009452448,0.0001225616],"domain_scores_gemma":[0.9995017,0.0002281029,0.00008387686,0.0001331191,0.00003071644,0.00002250276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000521267,0.0004985473,0.08097636,0.0001871482,0.0000596489,0.000002021666,0.001950964,0.00082889,0.1930976,0.06846762,0.0005238333,0.6533552],"study_design_scores_gemma":[0.001841615,0.0003160415,0.8600702,0.00001315619,0.000004520072,0.000002052747,0.0002790137,0.07552319,0.0472605,0.01440296,0.0001085995,0.0001781717],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5567009,0.00002859924,0.4422838,0.0003806573,0.00004277725,0.00034055,0.000001077135,0.00001162717,0.0002099153],"genre_scores_gemma":[0.8568273,0.00001532171,0.1428531,0.0000716542,0.00000662036,0.00008251816,0.0000036322,0.000003732936,0.0001362122],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7790938,"threshold_uncertainty_score":0.2401348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03358450317688975,"score_gpt":0.2952563527581573,"score_spread":0.2616718495812675,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}